这篇论文提出MADreMIA方法，用链式再生替代影子模型，显著提升对生成模型隐私泄露的检测灵敏度。
MADreMIA是一种模型无关的框架，利用链式再生迭代轨迹增强白盒、灰盒和黑盒下的成员推理（MIA）与数据集推理（DI）攻击。相较于依赖影子模型训练的传统方法，该方法通过复用生成输出作为输入，在低误报率下提升成员证据。实验表明，记忆训练样本在迭代再生中表现出更高一致性和更慢退化。论文在图像自回归模型、扩散模型和语言模型上进行了全面评估，并在音频模型上展示了初步结果。
Amplifying Membership Signal Through Chained Regeneration
The tendency of large generative models to memorize training data makes sample verification critical for privacy auditing and copyright enforcement. Current membership (MIA) and dataset inference (DI) attacks often rely on one-shot generations, which yield weak signals and limited sensitivity across modalities. Inspired by Model Autophagy Disorder (MAD), we introduce MADreMIA, a model-agnostic framework that enhances white-, gray-, and black-box MIA and DI. Rather than relying on shadow model training -- often infeasible for large generative models -- our framework facilitates scalable inference by leveraging inherent signals through iterative trajectories. This process utilizes chained generations across diverse modalities, where each output serves as the subsequent input, to improve membership evidence at low FPR. We demonstrate that memorized training samples exhibit significantly higher coherence and slower degradation during iterative regeneration than non-member generations. Our results show that MADreMIA provides richer signals across diverse model families and modalities; we present comprehensive evaluations for IARs, diffusion, and language models, alongside preliminary results demonstrating its potential for audio models.